Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to exerting influence or creating stress on someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating pressure or influence exerted on individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aces
    -0.85
    onym
    -0.83
    utan
    -0.77
    uchs
    -0.76
    SourceFile
    -0.74
    apest
    -0.73
    anuts
    -0.73
     Assass
    -0.71
    BuyableInstoreAndOnline
    -0.70
    icter
    -0.70
    POSITIVE LOGITS
    erous
    1.08
     shoulders
    0.84
     inaction
    0.83
     policymakers
    0.82
     brakes
    0.81
     governments
    0.77
     negotiators
    0.76
     readiness
    0.74
     resolve
    0.73
     reeling
    0.73
    Act Density 0.129%

    No Known Activations